Search Results for author:
Found 27 papers, 6 papers with code
llm-japanese-dataset v0: Construction of Japanese Chat Dataset for Large Language Models and its Methodology
There are two ways to support languages other than English by those LLMs: constructing LLMs from scratch or tuning existing models.
Joint Multimodal Learning with Deep Generative Models
As described herein, we propose a joint multimodal variational autoencoder (JMVAE), in which all modalities are independently conditioned on joint representation.
Score Transformer: Generating Musical Score from Note-level Representation
In this paper, we explore the tokenized representation of musical scores using the Transformer model to automatically generate musical scores.
SSM Meets Video Diffusion Models: Efficient Video Generation with Structured State Spaces
In the experiments, we first evaluate our SSM-based model with UCF101, a standard benchmark of video generation.
From Base to Conversational: Japanese Instruction Dataset and Tuning Large Language Models
We performed Low-Rank Adaptation (LoRA) tuning on both Japanese and English existing models using our instruction dataset.
End-to-end Training of Deep Boltzmann Machines by Unbiased Contrastive Divergence with Local Mode Initialization
We address the problem of biased gradient estimation in deep Boltzmann machines (DBMs).
Improving Bi-directional Generation between Different Modalities with Variational Autoencoders
However, we found that when this model attempts to generate a large dimensional modality missing at the input, the joint representation collapses and this modality cannot be generated successfully.
Neural Machine Translation with Latent Semantic of Image and Text
The report of earlier studies has introduced a latent variable to capture the entire meaning of sentence and achieved improvement on attention-based Neural Machine Translation.
Generative Adversarial Nets from a Density Ratio Estimation Perspective
Generative adversarial networks (GANs) are successful deep generative models.
Variational Domain Adaptation
It reformulates the posterior with a natural paring $\langle, \rangle: \mathcal{Z} \times \mathcal{Z}^* \rightarrow \Real$, which can be expanded to uncountable infinite domains such as continuous domains as well as interpolation.
Learning shared manifold representation of images and attributes for generalized zero-shot learning
To solve this, we propose a concept to learn a mapping that embeds both images and attributes to the shared representation space that can be generalized even for unseen classes by interpolating from the information of seen classes, which we refer to shared manifold learning.
Out-of-Distribution Detection Using Layerwise Uncertainty in Deep Neural Networks
However, on difficult datasets or models with low classification ability, these methods incorrectly regard in-distribution samples close to the decision boundary as OOD samples.
Iterative Image Inpainting with Structural Similarity Mask for Anomaly Detection
Moreover, there is objective mismatching that models are trained to minimize total reconstruction errors while we expect a small deviation on normal pixels and large deviation on anomalous pixels.
A Whole Brain Probabilistic Generative Model: Toward Realizing Cognitive Architectures for Developmental Robots
This approach is based on two ideas: (1) brain-inspired AI, learning human brain architecture to build human-level intelligence, and (2) a probabilistic generative model(PGM)-based cognitive system to develop a cognitive system for developmental robots by integrating PGMs.
Pixyz: a Python library for developing deep generative models
With the recent rapid progress in the study of deep generative models (DGMs), there is a need for a framework that can implement them in a simple and generic way.
Scalable multimodal variational autoencoders with surrogate joint posterior
A state-of-the-art approach to learning this aggregation of experts is to encourage all modalities to be reconstructed and cross-generated from arbitrary subsets.
Learning Global Spatial Information for Multi-View Object-Centric Models
Therefore, we introduce several crucial components which help inference and training with the proposed model.
Improving the Robustness to Variations of Objects and Instructions with a Neuro-Symbolic Approach for Interactive Instruction Following
An interactive instruction following task has been proposed as a benchmark for learning to map natural language instructions and first-person vision into sequences of actions to interact with objects in 3D environments.
DUAL SPACE LEARNING WITH VARIATIONAL AUTOENCODERS
However, when the dimension of multiclass labels is large, these models cannot change images corresponding to labels, because learning multiple distributions of the corresponding class is necessary to transfer an image.
Relation-based Generalized Zero-shot Classification with the Domain Discriminator on the shared representation
However, this relation-based approach presents a difficulty: many of the test images are predicted as biased to the seen domain, i. e., the \emph{domain bias problem}.
A survey of multimodal deep generative models
In recent years, deep generative models, i. e., generative models in which distributions are parameterized by deep neural networks, have attracted much attention, especially variational autoencoders, which are suitable for accomplishing the above challenges because they can consider heterogeneity and infer good representations of data.
World Models and Predictive Coding for Cognitive and Developmental Robotics: Frontiers and Challenges
Therefore, in this paper, we clarify the definitions, relationships, and status of current research on these topics, as well as missing pieces of world models and predictive coding in conjunction with crucially related concepts such as the free-energy principle and active inference in the context of cognitive and developmental robotics.
JMedLoRA:Medical Domain Adaptation on Japanese Large Language Models using Instruction-tuning
Furthermore, our results underscore the potential of adapting English-centric models for Japanese applications in domain adaptation, while also highlighting the persisting limitations of Japanese-centric models.
Personalized human mobility prediction for HuMob challenge
We adopted a personalized model to predict the individual's movement trajectory from their data, instead of predicting from the overall movement, based on the hypothesis that human movement is unique to each person.
Is ChatGPT the Future of Causal Text Mining? A Comprehensive Evaluation and Analysis
Causality is fundamental in human cognition and has drawn attention in diverse research fields.
JaFIn: Japanese Financial Instruction Dataset
To achieve this, we propose an instruction tuning data in Japanese called JaFIn, the Japanese Financial Instruction Dataset.
